File size: 10,006 Bytes
f5776d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
from collections import namedtuple
import re
from typing import Union, Any
import dsp
from dsp.primitives.demonstrate import Example
from .utils import passages2text, format_answers

Field = namedtuple("Field", "name separator input_variable output_variable description")

# TODO: de-duplicate with dsp/templates/template.py


class TemplateV2:
    def __init__(
        self,
        template,
        format_handlers={
            "passages": passages2text,
            "contexte": passages2text,
            "reponse": format_answers,
            "reponses": format_answers,
        },
    ):
        self.format_handlers = format_handlers

        template = template.strip()

        self.instructions = re.search("(.*)\n", template).group(1)
        template = template[len(self.instructions) :].strip()

        self.fields = []
        while len(template) > 0:
            match = re.search("(.*)(\s){(.*)}\s(.*\${.*})", template)
            if match is not None:
                name = match.group(1)
                separator = match.group(2)
                variable = match.group(3)
                description = match.group(4)
            else:
                match = re.search("(.*)(\s){(.*)}", template)
                if match is not None:
                    name = match.group(1)
                    separator = match.group(2)
                    variable = match.group(3)
                    description = None
                else:
                    raise ValueError(f"Could not parse template")

            var_match = re.match("(.*) -> (.*)", variable)
            if var_match is not None:
                input_variable = var_match.group(1)
                output_variable = var_match.group(2)
            else:
                input_variable = variable
                output_variable = variable

            self.fields.append(
                Field(
                    name=name,
                    separator=separator,
                    input_variable=input_variable,
                    output_variable=output_variable,
                    description=description,
                )
            )

            template = template[len(match.group(0)) :].strip()

    def query(self, example: Example, is_demo: bool = False) -> str:
        """Retrieves the input variables from the example and formats them into a query string."""
        result: list[str] = []

        if not is_demo:
            has_value = [
                field.input_variable in example
                and example[field.input_variable] is not None
                and example[field.input_variable] != ""
                for field in self.fields
            ]

            for i in range(1, len(has_value)):
                if has_value[i - 1] and not any(has_value[i:]):
                    example[self.fields[i].input_variable] = ""
                    break

        for field in self.fields:
            if (
                field.input_variable in example
                and example[field.input_variable] is not None
            ):
                if field.input_variable in self.format_handlers:
                    format_handler = self.format_handlers[field.input_variable]
                else:

                    def format_handler(x):
                        return " ".join(x.split())
                
                formatted_value = format_handler(example[field.input_variable])
                separator = '\n' if field.separator == ' ' and '\n' in formatted_value else field.separator

                result.append(
                    f"{field.name}{separator}{formatted_value}"
                )

        if self._has_augmented_guidelines() and ("augmented" in example and example.augmented):
            return "\n\n".join([r for r in result if r])
        return "\n".join([r for r in result if r])

    def guidelines(self, show_guidelines=True) -> str:
        """Returns the task guidelines as described in the lm prompt"""
        if (not show_guidelines) or (
            hasattr(dsp.settings, "show_guidelines")
            and not dsp.settings.show_guidelines
        ):
            return ""

        result = "Respecte le format suivant.\n\n"

        example = dsp.Example()
        for field in self.fields:
            example[field.input_variable] = field.description
        example.augmented = self._has_augmented_guidelines()

        result += self.query(example)
        return result

    def _has_augmented_guidelines(self):
        return len(self.fields) > 3 or any(
            ("\n" in field.separator) or ('\n' in field.description) for field in self.fields
        )

    def extract(
        self, example: Union[Example, dict[str, Any]], raw_pred: str
    ) -> Example:
        """Extracts the answer from the LM raw prediction using the template structure

        Args:
            example (Union[Example, dict[str, Any]]): Contains the input variables that raw_pred was completed on.
            raw_pred (str): LM generated string

        Returns:
            Example: The example with the output variables filled in
        """
        example = dsp.Example(example)

        raw_pred = raw_pred.strip()

        idx = 0
        while idx < len(self.fields):
            if (
                self.fields[idx].input_variable not in example
                or example[self.fields[idx].input_variable] is None
            ):
                break
            idx += 1

        import dspy

        idx = min(idx, len(self.fields) - 1)
        while raw_pred != "" and idx < len(self.fields):
            if idx < len(self.fields) - 1:
                next_field_name = "\n" + self.fields[idx + 1].name
                offset = raw_pred.find(next_field_name)

                if offset >= 0:
                    if dspy.settings.release >= 20231003:
                        example[self.fields[idx].output_variable] = raw_pred[:offset].strip().rstrip('---').strip()
                        raw_pred = raw_pred[offset + len(next_field_name) :].strip().rstrip('---').strip()
                    else:
                        example[self.fields[idx].output_variable] = raw_pred[:offset].strip()
                        raw_pred = raw_pred[offset + len(next_field_name) :].strip()

                    idx += 1
                else:
                    if dspy.settings.release >= 20231003:
                        example[self.fields[idx].output_variable] = raw_pred.strip().rstrip('---').strip()
                    else:
                        example[self.fields[idx].output_variable] = raw_pred.strip()

                    raw_pred = ""
                    idx += 1
                    break

            else:
                assert idx == len(self.fields) - 1, (idx, len(self.fields))

                if dspy.settings.release >= 20231003:
                    example[self.fields[idx].output_variable] = raw_pred.strip().rstrip('---').strip()
                else:
                    example[self.fields[idx].output_variable] = raw_pred.strip()

                break

        return example

    def __call__(self, example, show_guidelines=True) -> str:
        example = dsp.Example(example)

        if hasattr(dsp.settings, 'query_only') and dsp.settings.query_only:
            return self.query(example)

        # The training data should not contain the output variable
        if self.fields[-1].input_variable in example:
            del example[self.fields[-1].input_variable]

        rdemos = [
            self.query(demo, is_demo=True)
            for demo in example.demos
            if (
                ("augmented" not in demo or not demo.augmented)
                and (  # validate that the training example has the same primitive input var as the template
                    self.fields[-1].input_variable in demo
                    and demo[self.fields[-1].input_variable] is not None
                )
            )
        ]

        ademos = [
            self.query(demo, is_demo=True)
            for demo in example.demos
            if "augmented" in demo and demo.augmented
        ]

        # Move the rdemos to ademos if rdemo has all the fields filled in
        rdemos_ = []
        new_ademos = []
        for rdemo in rdemos:
            if all(
                (field.name in rdemo)
                for field in self.fields
                if field.input_variable in example
            ):
                import dspy

                if dspy.settings.release >= 20230928:
                    new_ademos.append(rdemo)
                else:
                    ademos.append(rdemo)
            else:
                rdemos_.append(rdemo)
        
        ademos = new_ademos + ademos
        rdemos = rdemos_


        long_query = self._has_augmented_guidelines()

        if long_query:
            example["augmented"] = True

        query = self.query(example)

        # if it has more lines than fields
        if len(query.split('\n')) > len(self.fields):
            long_query = True

            if "augmented" not in example or not example.augmented:
                example["augmented"] = True
                query = self.query(example)

        rdemos = "\n\n".join(rdemos)
        
        if len(rdemos) >= 1 and len(ademos) == 0 and not long_query:
            rdemos_and_query = "\n\n".join([rdemos, query])
            parts = [
                self.instructions,
                self.guidelines(show_guidelines),
                rdemos_and_query,
            ]
        elif len(rdemos) == 0:
            parts = [
                self.instructions,
                self.guidelines(show_guidelines),
                *ademos,
                query,
            ]
        else:
            parts = [
                self.instructions,
                rdemos,
                self.guidelines(show_guidelines),
                *ademos,
                query,
            ]

        prompt = "\n\n---\n\n".join([p.strip() for p in parts if p])

        return prompt.strip()